• Title/Summary/Keyword: feed-forward architecture

Search Result 3, Processing Time 0.078 seconds

Video Object Segmentation with Weakly Temporal Information

  • Zhang, Yikun;Yao, Rui;Jiang, Qingnan;Zhang, Changbin;Wang, Shi
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.13 no.3
    • /
    • pp.1434-1449
    • /
    • 2019
  • Video object segmentation is a significant task in computer vision, but its performance is not very satisfactory. A method of video object segmentation using weakly temporal information is presented in this paper. Motivated by the phenomenon in reality that the motion of the object is a continuous and smooth process and the appearance of the object does not change much between adjacent frames in the video sequences, we use a feed-forward architecture with motion estimation to predict the mask of the current frame. We extend an additional mask channel for the previous frame segmentation result. The mask of the previous frame is treated as the input of the expanded channel after processing, and then we extract the temporal feature of the object and fuse it with other feature maps to generate the final mask. In addition, we introduce multi-mask guidance to improve the stability of the model. Moreover, we enhance segmentation performance by further training with the masks already obtained. Experiments show that our method achieves competitive results on DAVIS-2016 on single object segmentation compared to some state-of-the-art algorithms.

An Implementation of Neuro-Fuzzy Based Land Convert Pattern Classification System for Remote Sensing Image (뉴로-퍼지 알고리즘을 이용한 원격탐사 화상의 지표면 패턴 분류시스템 구현)

  • 이상구
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.9 no.5
    • /
    • pp.472-479
    • /
    • 1999
  • In this paper, we propose a land cover pattern classifier for remote sensing image by using neuro-fuzzy algorithm. The proposed pattem classifier has a 3-layer feed-forward architecture that is derived from generic fuzzy perceptrons, and the weights are con~posed of h u y sets. We also implement a neuro-fuzzy pattern classification system in the Visual C++ environment. To measure the performance of this, we compare it with the conventional neural networks with back-propagation learning and the Maximum-likelihood algorithms. We classified the remote sensing image into the eight classes covered the majority of land cover feature, selected the same training sites. Experimental results show that the proposed classifier performs well especially in the mixed composition area having many classes rather than the conventional systems.

  • PDF

Design of the Low-Power Continuous-Time Sigma-Delta Modulator for Wideband Applications (광대역 시스템을 위한 저전력 시그마-델타 변조기)

  • Kim, Kunmo;Park, Chang-Joon;Lee, Sanghun;Kim, Sangkil;Kim, Jusung
    • Journal of IKEEE
    • /
    • v.21 no.4
    • /
    • pp.331-337
    • /
    • 2017
  • In this paper, we present the design of a 20MHz bandwidth 3rd-order continuous-time low-pass sigma-delta modulator with low-noise and low-power consumption. The bandwidth of the system is sufficient to accommodate LTE and other wireless network standards. The 3rd-order low-pass filter with feed-forward architecture achieves the low-power consumption as well as the low complexity. The system uses 3bit flash quantizer to provide fast data conversion. The current-steering DAC achieves low-power and improved sensitivity without additional circuitries. Cross-coupled transistors are adopted to reduce the current glitches. The proposed system achieves a peak SNDR of 65.9dB with 20MHz bandwidth and power consumption of 32.65mW. The in-band IM3 is simulated to be 69dBc with 600mVp-p two tone input tones. The circuit is designed in a 0.18-um CMOS technology and is driven by 500MHz sampling rate signal.